Model comparison
Ministral 8B vs Qwen-14B
Qwen-14B is the stronger model overall, scoring 31.4 to 28.2 on the Noometry Index.
Last verified . 10 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. Ministral 8B scores higher in 5 categories and Qwen-14B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Ministral 8B leads 39.6 to 27.6.
Side by side
| Ministral 8B | Qwen-14B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 28.2 | 31.4 |
| Released | 2024-10-01 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 17 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Ministral 8B leads
Ministral 8B: 35.0 (#230), Qwen-14B: 31.2 (#288)
| Benchmark | Ministral 8B | Qwen-14B |
|---|---|---|
| LMArena Coding | 1202 | 1071 |
Agentic & Tool Use Not comparable
Ministral 8B: 16.4 (#148), Qwen-14B: —
| Benchmark | Ministral 8B | Qwen-14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 11.1% | — |
Reasoning Qwen-14B leads
Ministral 8B: 18.4 (#281), Qwen-14B: 19.6 (#257)
| Benchmark | Ministral 8B | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1027 |
| DTBench | 45.7% | — |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 113.03 |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Qwen-14B leads
Ministral 8B: 25.7 (#267), Qwen-14B: 31.2 (#227)
| Benchmark | Ministral 8B | Qwen-14B |
|---|---|---|
| LMArena Math | 1188 | 1068 |
| MATH Level 5 | 14.9% | — |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Ministral 8B: 12.6 (#297), Qwen-14B: —
| Benchmark | Ministral 8B | Qwen-14B |
|---|---|---|
| GPQA Diamond | 27.1% | — |
| Vectara Hallucination Rate | 7.4% | — |
| LMArena Expert | 1170 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual Ministral 8B leads
Ministral 8B: 35.1 (#247), Qwen-14B: 27.5 (#275)
| Benchmark | Ministral 8B | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1165 | 1041 |
| LMArena Chinese | 1193 | 1077 |
| LMArena Russian | 1195 | — |
Instruction Following Ministral 8B leads
Ministral 8B: 60.5 (#250), Qwen-14B: 52.4 (#289)
| Benchmark | Ministral 8B | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1161 | 1031 |
Long Context Ministral 8B leads
Ministral 8B: 36.7 (#227), Qwen-14B: 31.3 (#280)
| Benchmark | Ministral 8B | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1212 | 1028 |
Writing & Preference Ministral 8B leads
Ministral 8B: 39.6 (#246), Qwen-14B: 27.6 (#299)
| Benchmark | Ministral 8B | Qwen-14B |
|---|---|---|
| LMArena Text | 1191 | 1051 |
| LMArena Creative Writing | 1175 | 1028 |
| LMArena Multi-Turn | 1166 | 1022 |
Frequently asked questions
Is Ministral 8B better than Qwen-14B?
Qwen-14B is the stronger model overall, scoring 31.4 to 28.2 on the Noometry Index.
Is Ministral 8B or Qwen-14B better for coding?
Ministral 8B scores higher on coding benchmarks: 35.0 versus 31.2 in the Noometry coding category.
How many benchmarks do Ministral 8B and Qwen-14B share?
10 benchmarks have published results for both models. Ministral 8B has 17 scored results on Noometry and Qwen-14B has 18.